Hongmin Cai

Multiparametric Tissue Characterization of Brain Neoplasms and Their Recurrence Using Pattern Classification of MR Images

RATIONALE AND OBJECTIVES Treatment of brain neoplasms can greatly benefit from better delineation of bulk neoplasm boundary and the extent and degree of more subtle neoplastic infiltration. Magnetic resonance imaging (MRI) is the primary imaging modality for evaluation before and after therapy, typically combining conventional sequences with more advanced techniques such as perfusion-weighted imaging and diffusion tensor imaging (DTI). The purpose of this study is to quantify the multiparametric imaging profile of neoplasms by integrating structural MRI and DTI via statistical image analysis methods to potentially capture complex and subtle tissue characteristics that are not obvious from any individual image or parameter. MATERIALS AND METHODS Five structural MRI sequences, namely, B0, diffusion-weighted images, fluid-attenuated inversion recovery, T1-weighted, and gadolinium-enhanced T1-weighted, and two scalar maps computed from DTI (ie, fractional anisotropy and apparent diffusion coefficient) are used to create an intensity-based tissue profile. This is incorporated into a nonlinear pattern classification technique to create a multiparametric probabilistic tissue characterization, which is applied to data from 14 patients with newly diagnosed primary high-grade neoplasms who have not received any therapy before imaging. RESULTS Preliminary results demonstrate that this multiparametric tissue characterization helps to better differentiate among neoplasm, edema, and healthy tissue, and to identify tissue that is likely to progress to neoplasm in the future. This has been validated on expert assessed tissue. CONCLUSION This approach has potential applications in treatment, aiding computer-assisted surgery by determining the spatial distributions of healthy and neoplastic tissue, as well as in identifying tissue that is relatively more prone to tumor recurrence.

Repulsive force based snake model to segment and track neuronal axons in 3D microscopy image stacks

The branching patterns of axons and dendrites are fundamental structural properties that affect the synaptic connectivity of axons. Although today three-dimensional images of fluorescently labeled processes can be obtained to study axonal branching, there are no robust methods of tracing individual axons. This paper describes a repulsive force based snake model to segment and track axonal profiles in 3D images. This new method segments all the axonal profiles in a 2D image and then uses the results obtained from that image as prior information to help segment the adjacent 2D image. In this way, the segmentation successfully connects axonal profiles over hundreds of images in a 3D image stack. Individual axons can then be extracted based on the segmentation results. The utility and performance of the method are demonstrated using 3D axonal images obtained from transgenic mice that express fluorescent protein.

Quantitative analysis and prediction of regional lymph node status in rectal cancer based on computed tomography imaging

ObjectivesTo quantitatively evaluate regional lymph nodes in rectal cancer patients by using an automated, computer-aided approach, and to assess the accuracy of this approach in differentiating benign and malignant lymph nodes.MethodsPatients (228) with newly diagnosed rectal cancer, confirmed by biopsy, underwent enhanced computed tomography (CT). Patients were assigned to the benign node or malignant node group according to histopathological analysis of node samples. All CT-detected lymph nodes were segmented using the edge detection method, and seven quantitative parameters of each node were measured. To increase the prediction accuracy, a hierarchical model combining the merits of the support and relevance vector machines was proposed to achieve higher performance.ResultsOf the 220 lymph nodes evaluated, 125 were positive and 95 were negative for metastases. Fractal dimension obtained by the Minkowski box-counting approach was higher in malignant nodes than in benign nodes, and there was a significant difference in heterogeneity between metastatic and non-metastatic lymph nodes. The overall performance of the proposed model is shown to have accuracy as high as 88% using morphological characterisation of lymph nodes.ConclusionsComputer-aided quantitative analysis can improve the prediction of node status in rectal cancer.

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer.

Using nonlinear diffusion and mean shift to detect and connect cross-sections of axons in 3D optical microscopy images.

The morphology of neuronal axons has been actively investigated by researchers to understand functionalities of neuronal networks, for example, in developmental neurology. Todays optical microscope and labeling techniques allow us to obtain high-resolution images about axons in three dimensions (3D), however, it remains challenging to segment and reconstruct the 3D morphology of axons. These include differentiating adjacent axons and detecting the axon branches. In this paper we present a method to track axons in 3D by identifying cross-sections of axons on 2D images and connecting the cross-sections over a series of 2D images to reconstruct the 3D morphology. The method can separate adjacent axons and detect the split and merge of axons. The method consists of three steps, modified nonlinear diffusion to remove noise and enhance edges in 2D, morphological operations to detect edges of the cross-sections of axons in 2D, and mean shift to track the cross-sections of axons in 3D. Performance of the method is demonstrated by processing real data acquired by confocal laser scanning microscopy.

Diagnostic assessment by dynamic contrast-enhanced and diffusion-weighted magnetic resonance in differentiation of breast lesions under different imaging protocols

BackgroundThe apparent diffusion coefficient (ADC) is a highly diagnostic factor in discriminating malignant and benign breast masses in diffusion-weighted magnetic resonance imaging (DW-MRI). The combination of ADC and other pictorial characteristics has improved lesion type identification accuracy. The objective of this study was to reassess the findings on an independent patient group by changing the magnetic field from 1.5-Tesla to 3.0-Tesla.MethodsThis retrospective study consisted of a training group of 234 female patients, including 85 benign and 149 malignant lesions, imaged using 1.5-Tesla MRI, and a test group of 95 female patients, including 19 benign and 85 malignant lesions, imaged using 3.0-Tesla MRI. The lesion of interest was segmented from the raw image and four sets of measurements describing the morphology, kinetics, DW-MRI, and texture of the pictorial properties of each lesion were obtained. Each lesion was characterized by 28 features in total. Three classical machine-learning algorithms were used to build prediction models on the training group, which evaluated the prognostic performance of the multi-sided features in three scenarios. To reduce information redundancy, five highly diagnostic factors were selected to obtain a compact yet informative characterization of the lesion status.ResultsThree classification models were built on the training of 1.5-Tesla patients and were tested on the independent 3.0-Tesla test group. The following results were found. i) Characterization of breast masses in a multi-sided way dramatically increased prediction performance. The usage of all features gave a higher performance in both sensitivity and specificity than any individual feature groups or their combinations. ii) ADC was a highly effective factor in improving the sensitivity in discriminating malignant from benign masses. iii) Five features, namely ADC, Sum Average, Entropy, Elongation, and Sum Variance, were selected to achieve the highest performance in diagnosis of the 3.0-Tesla patient group.ConclusionsThe combination of ADC and other multi-sided characteristics can increase the capability of discriminating malignant and benign breast lesions, even under different imaging protocols. The selected compact feature subsets achieved a high diagnostic performance and thus are promising in clinical applications for discriminating lesion type and for personalized treatment planning.

Molecular prognostic prediction for locally advanced nasopharyngeal carcinoma by support vector machine integrated approach.

Background Accurate prognostication of locally advanced nasopharyngeal carcinoma (NPC) will benefit patients for tailored therapy. Here, we addressed this issue by developing a mathematical algorithm based on support vector machine (SVM) through integrating the expression levels of multi-biomarkers. Methodology/Principal Findings Ninety-seven locally advanced NPC patients in a randomized controlled trial (RCT), consisting of 48 cases serving as training set and 49 cases as testing set of SVM models, with 5-year follow-up were studied. We designed SVM models by selecting the variables from 38 tissue molecular biomarkers, which represent 6 tumorigenesis signaling pathways, and 3 EBV-related serological biomarkers. We designed 3 SVM models to refine prognosis of NPC with 5-year follow-up. The SVM1 displayed highly predictive sensitivity (sensitivity, specificity were 88.0% and 81.9%, respectively) by integrating the expression of 7 molecular biomarkers. The SVM2 model showed highly predictive specificity (sensitivity, specificity were 84.0% and 94.5%, respectively) by grouping the expression level of 12 molecular biomarkers and 3 EBV-related serological biomarkers. The SVM3 model, constructed by combination SVM1 with SVM2, displayed a high predictive capacity (sensitivity, specificity were 88.0% and 90.3%, respectively). We found that 3 SVM models had strong power in classification of prognosis. Moreover, Cox multivariate regression analysis confirmed these 3 SVM models were all the significant independent prognostic model for overall survival in testing set and overall patients. Conclusions/Significance Our SVM prognostic models designed in the RCT displayed strong power in refining patient prognosis for locally advanced NPC, potentially directing future target therapy against the related signaling pathways.

Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach.

Purpose Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported. Materials and Methods The study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination. Results Seven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively. Conclusion Multi-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions.

Feature weight estimation for gene selection: a local hyperlinear learning approach

BackgroundModeling high-dimensional data involving thousands of variables is particularly important for gene expression profiling experiments, nevertheless,it remains a challenging task. One of the challenges is to implement an effective method for selecting a small set of relevant genes, buried in high-dimensional irrelevant noises. RELIEF is a popular and widely used approach for feature selection owing to its low computational cost and high accuracy. However, RELIEF based methods suffer from instability, especially in the presence of noisy and/or high-dimensional outliers.ResultsWe propose an innovative feature weighting algorithm, called LHR, to select informative genes from highly noisy data. LHR is based on RELIEF for feature weighting using classical margin maximization. The key idea of LHR is to estimate the feature weights through local approximation rather than global measurement, which is typically used in existing methods. The weights obtained by our method are very robust in terms of degradation of noisy features, even those with vast dimensions. To demonstrate the performance of our method, extensive experiments involving classification tests have been carried out on both synthetic and real microarray benchmark datasets by combining the proposed technique with standard classifiers, including the support vector machine (SVM), k-nearest neighbor (KNN), hyperplane k-nearest neighbor (HKNN), linear discriminant analysis (LDA) and naive Bayes (NB).ConclusionExperiments on both synthetic and real-world datasets demonstrate the superior performance of the proposed feature selection method combined with supervised learning in three aspects: 1) high classification accuracy, 2) excellent robustness to noise and 3) good stability using to various classification algorithms.

Effective image noise removal based on difference eigenvalue

Preservation of fine feature of an image is essential during the process of noise removal, especially via some types of smoothing such as using diffusion process-based methods to enhance images. In this paper, we present a new edge indicator called difference eigenvalue to measure image gradient magnitude in the diffusion process. Based on the eigenvalues of the Hessian matrix, the difference eigenvalue manifest itself in terms of structural information of an image. We adapt the new edge indicator to a diffusion model to achieve a better balance between noise removal and detail preservation. Experiments on both synthetic and real images show that the new model can obtain good results and outperforms existing methods.